Sökning: "SSIM"

Visar resultat 1 - 5 av 55 uppsatser innehållade ordet SSIM.

1. 1. Limited angle reconstruction for 2D CT based on machine learning

   Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)

   Författare :Eric Oldgren; Knut Salomonsson; [2023]
   Nyckelord :CT; computed tomography; limited angle; machine learning; limited data; ill posed problem; inverse problem;

   Sammanfattning : The aim of this report is to study how machine learning can be used to reconstruct 2 dimensional computed tomography images from limited angle data. This could be used in a variety of applications where either the space or timeavailable for the CT scan limits the acquired data.In this study, three different types of models are considered. LÄS MER

3. 2. Analyzing the Influence of Synthetic andAugmented Data on Segmentation Model

   Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Författare :Alex Peschel; [2023]
   Nyckelord :Artificial Intelligence; Microorganisms; Segmentation; Synthesizing; Augmentation;

   Sammanfattning : The field of Artificial Intelligence (AI) has experienced unprecedented growth in recent years, thanks to the numerous applications related to speech recognition, natural language processing, and computer vision. However, one of the challenges facing AI is the requirement for large amounts of energy, time, and data to be effective and accurate. LÄS MER

4. 3. Using Generative Adversarial Networks for H&E-to-HER2 Stain Translation in Digital Pathology Images

   Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknik

   Författare :William Tirmén; [2023]
   Nyckelord :Machine learning; Artificial intelligence; Digital pathology; Image processing; Generative adversarial networks; Image-to-image translation;

   Sammanfattning : In digital pathology, hematoxylin & eosin (H&E) is a routine stain which is performed on most clinical cases and it often provides clinicians with sufficient information for diagnosis. However, when making decisions on how to guide breast cancer treatment, immunohistochemical staining of human epidermal growth factor 2 (HER2 staining) is also needed. LÄS MER

5. 4. Prediction of the gain in classification performance from combining multiple imaging modalities

   Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Roman Denkin; [2023]
   Nyckelord :;

   Sammanfattning : In this work, we investigate the relationship between different image modalities and classification performance, aiming to predict the potential gain in classification accuracy when combining multiple modalities. We analyze mathematical and statistical measures and develop novel reconstruction measures (RMSE and RSSIM) to assess information distribution between different image modalities. LÄS MER

7. 5. En jämförelse av Deep Learning-modeller för Image Super-Resolution

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Rafael Bechara; Max Israelsson; [2023]
   Nyckelord :Bachelor’s thesis; Image Super-Resolution; Deep Learning models; EDSR; LapSRN; ESPCN; FSRCNN; resolution enhancement; low-resolution images; quantitative evaluation; RMSE; PSNR; SSIM; Abyssinian cats; dataset; image quality.; Kandidatexamensarbete; Image Super-Resolution; EDSR; LapSRN; ESPCN; FSRCNN; Djupinlärningsmodeller; upplösningsförbättring; lågupplösta bilder; kvantitativ utvärdering; RMSE; PSNR; SSIM; abyssinska katter; datamängd; bildkvalitet.;

   Sammanfattning : Image Super-Resolution (ISR) is a technology that aims to increase image resolution while preserving as much content and detail as possible. In this study, we evaluate four different Deep Learning models (EDSR, LapSRN, ESPCN, and FSRCNN) to determine their effectiveness in increasing the resolution of lowresolution images. LÄS MER